Long-Tailed 3D Semantic Segmentation with Adaptive Weight Constraint and Sampling
Lists
Only you see this
Abstract
Existing 3D understanding datasets typically provide annotations for a limited number of object classes, with sufficient examples per class. However, real-world object classes are not equally represented in practical settings, leading to poor performance on rarely-occurring categories if the class imbalance is neglected. In this work, we address the challenge of 3D semantic segmentation with a long-tail distribution of classes. Common methods to reduce class imbalance during training include data re-sampling, loss re-weighting, and transfer learning. In contrast, our work proposes to effectively utilize network classifier weights in 3D models to balance the training on long-tail class distributions. While previous work in the 2D domain has studied imposing constraints on the classifier weights to regularize the training, it is sensitive to hyper-parameter choices and has not been yet explored for the 3D domain. To address these challenges, our work proposes adaptive regularization for frequent classes and sampling-based regularization for rare classes that alleviate the need to manually select thresholds and can dynamically focus training on the hard classes. Our experiments on the large-scale Scan-Net200 benchmark show that our method achieves improved performance, surpassing methods that rely on re-sampling, re-weighting, and pre-training.
BibTeX
@inproceedings{lahoud2024long,
author = {Jean Lahoud and Fahad Shahbaz Khan and Hisham Cholakkal and Rao Muhammad Anwer and Salman H. Khan},
title = {{Long-Tailed 3D Semantic Segmentation with Adaptive Weight Constraint and Sampling}},
booktitle = {IEEE International Conference on Robotics and Automation},
year = {2024},
doi = {10.1109/icra57147.2024.10610029},
}Loading related content...